Elabidine et al. (2025) Harnessing CNN for flood mapping: Insights from Landsat-8 imagery

⚠️ Warning: This summary was generated from the abstract only, as the full text was not available.

Identification

• Journal: Springer Link (Chiba Institute of Technology)
• Year: 2025
• Date: 2025-12-11
• Authors: Imane Zine Elabidine, Anas Bahi, Tarik Saouabei, Fatiha Chouikri
• DOI: 10.1051/e3sconf/202567503004/pdf

Research Groups

Not specified in the provided text.

Short Summary

This study developed a practical method for flood mapping in the Zat sub-basin, Morocco, utilizing a U-Net Convolutional Neural Network on freely available Landsat-8 satellite imagery and SRTM elevation data, achieving high accuracy in detecting flooded areas.

Objective

• To map flood inundation areas in the Zat sub-basin using a U-Net Convolutional Neural Network applied to satellite imagery and elevation data.

Study Configuration

• Spatial Scale: Zat sub-basin within the Tensift Basin, Morocco.
• Temporal Scale: Pre- and post-flood events.

Methodology and Data

• Models used: U-Net Convolutional Neural Network (CNN), OTSU automatic thresholding method.
• Data sources: Landsat-8 satellite imagery, SRTM (Shuttle Radar Topography Mission) elevation data, Google Earth Engine (GEE) for processing.

Main Results

• The trained U-Net CNN model achieved a precision of approximately 96%.
• An F1-score of 0.84 was obtained.
• An Intersection over Union (IoU) of 0.73 was achieved.
• The model demonstrated reliable detection of flooded areas in complex topographic settings, such as the Tensift Basin.

Contributions

• Development and application of a practical flood mapping method using freely available Landsat-8 imagery and Google Earth Engine.
• Demonstration of the effectiveness of a U-Net CNN model combined with elevation data for flood detection in complex mountainous regions.
• Provision of a reliable tool for identifying flooded areas in regions prone to significant environmental and economic damage.

Funding

Not specified in the provided text.

Citation

@article{Elabidine2025Harnessing,
  author = {Elabidine, Imane Zine and Bahi, Anas and Saouabei, Tarik and Chouikri, Fatiha},
  title = {Harnessing CNN for flood mapping: Insights from Landsat-8 imagery},
  journal = {Springer Link (Chiba Institute of Technology)},
  year = {2025},
  doi = {10.1051/e3sconf/202567503004/pdf},
  url = {https://doi.org/10.1051/e3sconf/202567503004/pdf}
}